jaredpalmer/kev
Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own
Older snapshot: check the original source for current information.
From the publisher
README & documentation
Source previewRead the project’s overview, installation instructions and usage examples. The original README is the source of truth.
Small Jev-like decision models you can train and run yourself. Kev is a family of small decision models built on Qwen3.5 and Qwen3.8 and based on the architecture described in Jev's Architecture Unmasked. You can use the pretrained weights or train your own. The API matches TypeSafe's System One, so you can point their Python SDK at your local server. Start with Kev-4B. Move to Kev-9B if you have a bigger GPU, or to Kev-27B if you have an 80 GB GPU and want the most accurate Kev. Use Kev-0.8B when size matters more than accuracy. "Held-out datasets" is the chance-corrected index of the community Decision Index, scored on the test split of breadth-v1: 14 public datasets in five areas that no Kev trained on. "Validated context" is the longest document, in tokens, for which accuracy on real contracts (CUAD) stays within 3 points of the same model's accuracy at…
Read the full README ↗ · Preview checked 2026-11-02T22:52:16.930Z
Inside the original README — Document outline
- Kev
- Highlights
- Models
- Kev 1.0
- Quick Start
- Try It in the Browser
- Run It Locally
- Use It From Python
- Fine-Tune on Your Own Data
- With a Coding Agent
- By Hand
- Deploy Your Own Endpoint
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the README
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: Apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
What this repository does
Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own
Repository facts
- Owner
- jaredpalmer
- Primary language
- Python
- Stars
- 9,256
- Forks
- 623
- Open issues + pull requests
- 33
- License
- Apache-2.0
- Archived
- No
- Default branch
- main
- Created
- 2026-09-17T20:49:39.000Z
- Last push
- 2026-10-16T13:42:00.000Z
Topics and intended use
Owner-supplied topics: decision-model, jev, qwen3
Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.
Evaluate before installing
Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.
Source and freshness
Source: GitHub. Metadata observed 2026-10-17T12:10:02.740Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related repositories
EbookFoundation/free-programming-books
donnemartin/system-design-primer